Deep neural network based continuous speech recognition for Serbian using the Kaldi toolkit B Popović, S Ostrogonac, E Pakoci, N Jakovljević, V Delić Speech and Computer: 17th International Conference, SPECOM 2015, Athens …, 2015 | 35 | 2015 |
Improvements in Serbian speech recognition using sequence-trained deep neural networks E Pakoci, B Popović, DJ Pekar Информатика и автоматизация 3 (58), 53-76, 2018 | 18 | 2018 |
Voice assistant application for the Serbian language B Popović, E Pakoci, N Jakovljević, G Kočiš, D Pekar 2015 23rd Telecommunications Forum Telfor (TELFOR), 858-861, 2015 | 18 | 2015 |
Using morphological data in language modeling for Serbian large vocabulary speech recognition E Pakoci, B Popović, D Pekar Computational intelligence and neuroscience 2019 (1), 5072918, 2019 | 16 | 2019 |
Morphology-based vs unsupervised word clustering for training language models for Serbian S Ostrogonac, E Pakoci, M Sečujski, D Mišković Acta Polytechnica Hungarica: Journal of Applied Sciences, 2019 | 13 | 2019 |
End-to-end large vocabulary speech recognition for the Serbian language B Popović, E Pakoci, D Pekar Speech and Computer: 19th International Conference, SPECOM 2017, Hatfield …, 2017 | 13 | 2017 |
Language model optimization for a deep neural network based speech recognition system for Serbian E Pakoci, B Popović, D Pekar Speech and Computer: 19th International Conference, SPECOM 2017, Hatfield …, 2017 | 12 | 2017 |
Large vocabulary continuous speech recognition for Serbian using the Kaldi toolkit B Popović, E Pakoci, S Ostrogonac, D Pekar Proceedings of 10th Conference on Digital Speech and Image Processing (DOGS …, 2014 | 12 | 2014 |
Building a speech repository for a Serbian LVCSR system S Suzić, S Ostrogonac, E Pakoci, M Bojanić Telfor Journal 6 (2), 109-114, 2014 | 9 | 2014 |
A comparison of language model training techniques in a continuous speech recognition system for Serbian B Popović, E Pakoci, D Pekar Speech and Computer: 20th International Conference, SPECOM 2018, Leipzig …, 2018 | 7 | 2018 |
A phonetic segmentation procedure based on hidden markov models E Pakoci, B Popović, N Jakovljević, D Pekar, F Yassa Speech and Computer: 18th International Conference, SPECOM 2016, Budapest …, 2016 | 7 | 2016 |
HMM-based speech synthesis for the Serbian language E Pakoci, R Mak Proceedings of the 56th ETRAN Conference, 1-4, 2012 | 7 | 2012 |
Advanced voice activity detection on mobile phones by using microphone array and phoneme-specific Gaussian mixture models B Popović, E Pakoci, D Pekar 2016 IEEE 14th International Symposium on Intelligent Systems and …, 2016 | 5 | 2016 |
Transfer leaming in automatic speech recognition for Serbian B Popović, E Pakoci, D Pekar 2019 27th Telecommunications Forum (TELFOR), 1-4, 2019 | 3 | 2019 |
Recurrent neural networks and morphological features in language modeling for Serbian ET Pakoci, BZ Popović 2021 29th Telecommunications Forum (TELFOR), 1-8, 2021 | 2 | 2021 |
Methods for using class based n-gram language models in the Kaldi toolkit E Pakoci, B Popović International Conference on Speech and Computer, 492-503, 2021 | 2 | 2021 |
Automatic speech recognition system for dictating medical findings B Popović, E Pakoci, D Pekar Proc. of IcETRAN, 12-17, 2020 | 2 | 2020 |
Subjective assessment of text to speech synthesis systems for the Serbian language E Pakoci, R Mak, S Ostrogonac 2012 20th Telecommunications Forum (TELFOR), 732-735, 2012 | 2 | 2012 |
Overcoming data sparsity in automatic transcription of dictated medical findings E Pakoci, D Pekar, B Popović, M Sečujski, V Delić 2022 30th European Signal Processing Conference (EUSIPCO), 454-458, 2022 | 1 | 2022 |
Transfer learning for domain and environment adaptation in Serbian ASR BZ Popović, ET Pakoci, DJ Pekar Telfor Journal 12 (2), 110-115, 2020 | 1 | 2020 |